bestmodel.run / model — Muse-Glimmer-30B-GGUF (agent view)

category chat · unsloth/Muse-Glimmer-30B-GGUF · 12 runs in the model record
answer: 33.3 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  Arc Pro B70 32GB ×4                | 8-bit | 161.9 tok/s    | reported | ttft 2,872ms | vram - GB | ctx 32,768
  Radeon AI Pro R9700 32GB           | 4-bit | 33.2 tok/s     | reported | ttft 478ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 32GB           | 5-bit | 25.8 tok/s     | reported | ttft 559ms | vram - GB | ctx 2,048
  RTX 3060 12GB ×2                   | 4-bit | 37.8 tok/s     | reported | ttft 1,388ms | vram 17.3 GB | ctx 65,536
  RTX 3080 12GB                      | 3-bit | 13.8 tok/s     | reported | ttft 2,811ms | vram 9.4 GB | ctx 16,384
  RTX 3090 24GB ×2                   | 6-bit | 31.7 tok/s     | reported | ttft 176ms | vram - GB | ctx 2,048
  RTX 4060 Ti 16GB ×2                | 6-bit | 44 tok/s       | reported | ttft -ms | vram - GB | ctx 125,000
  RTX PRO 6000 Blackwell 96GB        | 8-bit | 48.1 tok/s     | reported | ttft 402ms | vram 32.8 GB | ctx 131,072